菜单
Sentry error monitoring and user behavior tracking via CLI. Use when: (1) debugging user-reported issues, (2) checking recent errors/crashes, (3) tracing user actions before an error occurred, (4) searching issues by user email, (5) user asks "Sentryのログを確認して" or similar.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Turn the current conversation content into a visually scannable HTML page, publish it to a personal S3 bucket, and return a short shareable URL. Use when (1) the user asks to "make this an HTML / link / browser-viewable page" (in any language, e.g. "HTML化して", "リンクで渡して", "ブラウザで見れる形に"), (2) "upload to s3" / "s3に上げて" is requested, (3) the content has tables, code, comparisons, charts, timelines, or diagrams that Markdown chat can't convey well, (4) the output is something the user wants to come back to later.
A skill that extracts keyframes from video files and analyzes their content. Automatically removes duplicate frames and optimizes image quality to reduce token consumption. Use when: - User provides a video file (.mp4, .mov, .avi, etc.) - User requests "watch this video", "analyze this video", "what's in this video" - Checking screen recordings or screencasts - Keyframe extraction is needed from video
Generate and edit images using Google Gemini or OpenAI GPT Image models. Automatically used for requests like "generate an image", "create an illustration", "edit this image". Also supports sticker sheet generation and splitting for requests like "create some stickers" or "generate multiple icons and split them". Choose between Gemini (Nano Banana) and OpenAI (gpt-image-1.5) providers.
| name | sentry-monitor |
| description | Sentry error monitoring and user behavior tracking via CLI. Use when: (1) debugging user-reported issues, (2) checking recent errors/crashes, (3) tracing user actions before an error occurred, (4) searching issues by user email, (5) user asks "Sentryのログを確認して" or similar. |
CLI-based Sentry monitoring for debugging user issues.
重要: Sentryログの確認にはTaskエージェント（haiku）を使用して高速に検索する。
Task tool:
subagent_type: "general-purpose"
model: "haiku"
prompt: "Sentryのログを確認して、VLM関連のイベントを探してください。以下のコマンドを実行して結果を報告: python3 ~/.claude/skills/sentry-monitor/scripts/sentry_api.py issues --all --limit 20"
Required environment variables:
# Required: Sentry API token
# Get from: https://sentry.io/settings/auth-tokens/
export SENTRY_AUTH_TOKEN="your-token"
# Required: Your Sentry organization slug
export SENTRY_ORG="your-org"
# Required: Your Sentry project slug
export SENTRY_PROJECT="your-project"
Add these to your ~/.zshenv or ~/.bashrc.
SCRIPT="~/.claude/skills/sentry-monitor/scripts/sentry_api.py"
# List unresolved issues (last 24h)
python3 $SCRIPT issues
# List all issues (including resolved)
python3 $SCRIPT issues --all
# Search with query
python3 $SCRIPT issues --query "level:error"
python3 $SCRIPT issues --query "is:unresolved has:user"
# Events from last 7 days
python3 $SCRIPT events --period 7d
# Issue details
python3 $SCRIPT issue <ISSUE_ID>
# User actions (breadcrumbs) before error
python3 $SCRIPT breadcrumbs <ISSUE_ID>
# Search by user email
python3 $SCRIPT user test@example.com
| Query | Description |
|---|---|
is:unresolved | Unresolved issues (default) |
is:resolved | Resolved issues |
level:error | Error level only |
level:warning | Warning level only |
user.email:X | Filter by user email |
has:user | Issues with user info |
python3 $SCRIPT issuespython3 $SCRIPT issue <ID>python3 $SCRIPT breadcrumbs <ID>python3 $SCRIPT user <EMAIL> (when user reports problem)| Variable | Required | Description |
|---|---|---|
SENTRY_AUTH_TOKEN | Yes | API token from Sentry |
SENTRY_ORG | Yes | Your Sentry organization slug |
SENTRY_PROJECT | Yes | Your Sentry project slug |